Asee peer logo

Combining Wavelets And The Hotelling Transform In Image Query

Download Paper |


1999 Annual Conference


Charlotte, North Carolina

Publication Date

June 20, 1999

Start Date

June 20, 1999

End Date

June 23, 1999



Page Count


Page Numbers

4.131.1 - 4.131.14

Permanent URL

Download Count


Request a correction

Paper Authors

author page

Sol Neeman

Download Paper |

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract

Session 2265

Combining Wavelets and the Hotelling Transform in Image Query

Sol Nocxr-1~ Johnson and Wales University


Image query has many applications in different areas, e.g., multimedia, satel- lite data base images and medical imaging. One of the strategies used in image query is the content based approach, in which the query image is pro vided hv the u9pr either as a rouch sketch or a coarse image from a scanner or -J 1__-L__ _1_1____ _.________~~~~~ ~~ -- a video camera. When the image data base is very large and the query image is only an appr oximation of the target image, straight forward comparisons using L1 or L2 metrics are not effective. Wavelets were found to be a good tool in these cases as they can be designed not to be sensitive to certain de- grees of distortion of the query image and at the same time give more weight to sign&ant features which closely match, providing fast and efficient image retrieval at interactive rates. While this method is more robust to distortion of the image due to translation and rotation compared with the L’ or L2 metrics, still the error is significant. In this paper, we provide some experimental results on this sensitivity and suggest the integration of the Hotelling transform in the query process CM. U” ;-,,, UlL~&“ G “ +I& .Y*ntYGt;,4t.,TXTP “ Ail xJ,1-DKxro*urvl” .*ti - 11 J. olor, rl;cw,*an u fsxxr nmcd-inne ~~u.zio 0 &"I" \I-"'"- rr&8wxant tn &_"._I" "V

the content based strategy that represents an image by a set of the largest wavelet coefficients in the query process,

1. Introduction In the “content based” image query, also referred to as “query by exam- ple” , ” similarity retrieval” or “sketch retrieval” the query image is provided , by the user either as a sketch of the object or as the output of a scanner or a video camera. Some of the difficulties associated with content based image query are described in [I], e.g., significant differences between the “ query image” and the ” target image” Artifacts and poor resolution of the query .

Neeman, S. (1999, June), Combining Wavelets And The Hotelling Transform In Image Query Paper presented at 1999 Annual Conference, Charlotte, North Carolina.

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 1999 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015